Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Cambridge Dictionary URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oxford
    0.96
    Oxford
    0.95
     oxford
    0.80
     Oxfordshire
    0.71
     OX
    0.67
    OX
    0.64
     ऑक्स
    0.62
     oks
    0.61
    Ox
    0.61
     Bod
    0.58
    POSITIVE LOGITS
     investigative
    0.41
    滃
    0.39
     Chili
    0.38
     proc
    0.37
     misconceptions
    0.37
     planar
    0.36
     chili
    0.35
     incorrect
    0.35
    ursive
    0.35
    ugi
    0.34
    Act Density 0.001%

    No Known Activations